-
Hi,
I guess this is more a general question about training a CNN but YOLO is the one i'm using. I've started my training set for 'person' detections by labelling some data from different cameras vi…
-
Hello,
it would be great if we could add support to pass a List of dataclasses:
```python
@dataclass
class ExperimentParams(Serializable):
@dataclass
class LayerParams:
…
-
We've gotten some good responses on our survey (https://github.com/deepchem/deepchem/issues/1722) about the future of DeepChem, and are starting to think about synthesizing the responses together. As …
-
Hey Patrick,
I have been using Equinox for one of my projects and up until now it has helped immensely in using JAX effectively and seamlessly.
For this project, I was going to use the model of…
-
Can you give details of your model and the datasets that you trained on?
-
Pose a question about one of the following articles:
[“The Geometry of Culture: Analyzing the Meanings of Class through Word Embeddings.”](https://journals.sagepub.com/doi/full/10.1177/00031224198…
-
Hello!
I was wondering if there is an example of a 3D Steerable CNN (using R3Conv). Furthermore, Is it possible to use this library to train a model using a tensor of shape (batch, channels, width, …
-
Thank you very much for your research and the sharing of the code。
but I have some questions
in generate_coordinates:
theta = torch.round(10000. * theta) / 10000.
Variable(coords, requires_grad=Fa…
-
Since we can handle generic graph-networks now, it's time to implement LSTM/RNN. Milestones:
- [ ] Add a basic LSTM cell (equivalent to TF's BasicLSTMCell)
- [ ] Modify network class to handle sequent…
nyanp updated
7 years ago
-
It would be nice to make BigGAN more like StyleGAN in a few ways, primarily its stability. StyleGAN also seems to have a better latent space with more disentangled and linearized factors, which is gre…
gwern updated
3 years ago